Your AI agent isn't lazy. It's homeless.
No desk. No tools. No idea what "done" means.
So you became its harness, its loop and its graph.
I broke down how to stop babysitting it in 10 steps ↓
holy f*ck... FSD V15 shows you exactly where it's going to park. so I made Grok Bot find and book that spot before I even got there
Elon says you can just tap the screen to move the spot. my concept demo works the same way, it just starts earlier: at "where do we even park"
one message to Grok Bot on the way to My wedding: "find us parking near the venue. covered, it's raining. under $20"
here's exactly what it did while I drove:
→ checked 3 garages and 41 street spots. street spots opened up, but it's raining: SKIP
→ Main St Garage, $22: SKIP. over budget
→ Congress Ave Garage, level 2, covered, 3 min walk, $14 until midnight: ASKED ME. it doesn't pay without my yes
→ same idea as V15: chevrons on the map show the exact spot it picked. I tapped 207 next to the elevator, it moved me. same price
→ EV charging in that spot was +$6. that's my money, so it asked. I said no
→ gate pass to Wallet, texted Mia where we parked (signed Grok Bot), reminder that garage entry closes at 1 AM
so the $9 open-air lot right there? cheaper, still a no. I said covered
44 spots, under 2 minutes, $14 total. laps around the block: 0
FSD parks the car. Grok Bot makes sure there's a spot waiting
what should it handle on your next drive?
3
24
748
Holy f*ck... Grok Bot booked a hotel for me in LA
i wedding in Los Angeles in 3 days. I needed a hotel for 2, close to the venue, under $300. one message, zero tabs opened
what it did:
→ checked 38 hotels, kept only 4: within 10 min of the venue + free cancellation
→ skipped the closest one because it had no free cancellation
→ compared 5 booking sites. same room was $40 cheaper booked direct
→ "The Lantern House, 2 nights, $238, free cancellation until Thu. book it?" it didn't book on its own. it asked me
→ messaged the front desk: early check-in at 1 PM and a quiet room, both free
→ late checkout was $30. that's money, so it asked first. I said yes
→ added it to my calendar, room key to Wallet, texted Mia (signed Grok Bot)
4 minutes. $268 total, $32 under budget
3 rules I gave it once:
1. book only what I asked for
2. anything that costs money: ask me first
3. stay under my budget
where should Grok Bot book you next?
Holy f*ck... Grok Bot booked a hotel for me in LA
i wedding in Los Angeles in 3 days. I needed a hotel for 2, close to the venue, under $300. one message, zero tabs opened
what it did:
→ checked 38 hotels, kept only 4: within 10 min of the venue + free cancellation
→ skipped the closest one because it had no free cancellation
→ compared 5 booking sites. same room was $40 cheaper booked direct
→ "The Lantern House, 2 nights, $238, free cancellation until Thu. book it?" it didn't book on its own. it asked me
→ messaged the front desk: early check-in at 1 PM and a quiet room, both free
→ late checkout was $30. that's money, so it asked first. I said yes
→ added it to my calendar, room key to Wallet, texted Mia (signed Grok Bot)
4 minutes. $268 total, $32 under budget
3 rules I gave it once:
1. book only what I asked for
2. anything that costs money: ask me first
3. stay under my budget
where should Grok Bot book you next?
Holy f*ck... Elon Musk's team makes airline help desk lines useless..
built a concept demo: JFK → LA delayed 3h40, 40 people at the desk ahead of me. Grok Bot sorted it before the line moved 3 people
it makes phone calls. it sits on hold, talks to the agent and says up front it's an AI
what it did while I sat at the gate:
→ sat through 9 minutes of hold music and beat the phone menu
→ got the airline to confirm it was a crew delay, so their delay promise applies
→ meal vouchers for both of us, straight to the app
→ "$500 in travel credit or $300 cash?" it didn't pick. it asked me. I took the cash
→ got the delay in writing for my records
→ texted Ana the new landing time (signed Grok Bot) and moved the Airbnb check-in
14 minutes on the phone. I walked away from the desk, 38 people still in line
all it takes is 3 rules you send Grok Bot once:
1. on every call, say you're an AI calling for me
2. ask for everything I'm owed, nothing made up
3. anything that costs money: ask me first
what should Grok Bot call for you next?
Holy f*ck.. Anthropic researcher Tao Lin, who works on safeguards for Claude, just said:
"I think that all humans on earth will become permanently unemployable and will need to strictly rely on government welfare to sustain themselves"
In the same 2.5 minutes:
→ His timeline to "broadly superhuman AI" is about 1.3 years: "end of 2027, something like that"
→ He means AI "as good as or better than the best expert at almost every field". Programming, making movies, "politics or literally anything"
→ To people angry at the ones building AI: "you're like totally right to feel angry"
→ Asked if it happens within the next 15 months, he says "No". There "aren't enough robots yet", so the capability comes first and the billions of robots come later
His first step is everyone losing their current job and moving to a new one. The ones who move first are the people whose agents already do the work
Bookmark it and watch tonight
I wrote the full course on building the harness that runs those agents for you ↓
Your AI agent isn't lazy. It's homeless.
No desk. No tools. No idea what "done" means.
So you became its harness, its loop and its graph.
I broke down how to stop babysitting it in 10 steps ↓
3
28
1,201
holy f*ck... Grok Bot 1.0 just turned my GTA 6 phone into a money printer
I connected Grok Bot to my phone in GTA 6 and just kept driving the boat
it ran the whole phone on its own:
→ scrolled my X feed so I didn't have to
→ caught a coin trending in my feed, up 382% that day
→ asked before spending a cent. I hit confirm
→ sold at +412%. +$2,060 while I steered
→ called a yacht club, said up front it's an AI, held a 42ft yacht for 9 PM
→ didn't pay for it. left that to me
one minute. I never touched a single menu
all it took was 3 rules:
1. on every call, say you're an AI
2. never make anything up
3. anything that costs money: ask me first
that was ONE bot
now picture 300 of them running a whole company
no bot #6 copying bot #5. no bot #30 burning your weekly limit
the full setup is in my article. read it below ↓
holy f*ck... Grok Bot 1.0 just turned my GTA 6 phone into a money printer
I connected Grok Bot to my phone in GTA 6 and just kept driving the boat
it ran the whole phone on its own:
→ scrolled my X feed so I didn't have to
→ caught a coin trending in my feed, up 382% that day
→ asked before spending a cent. I hit confirm
→ sold at +412%. +$2,060 while I steered
→ called a yacht club, said up front it's an AI, held a 42ft yacht for 9 PM
→ didn't pay for it. left that to me
one minute. I never touched a single menu
all it took was 3 rules:
1. on every call, say you're an AI
2. never make anything up
3. anything that costs money: ask me first
that was ONE bot
now picture 300 of them running a whole company
no bot #6 copying bot #5. no bot #30 burning your weekly limit
the full setup is in my article. read it below ↓
holy f*ck... Claude Code just made Rockstar with GTA 6 useless..
Rockstar has been building GTA 6 for 12 years. 2,000+ devs. $2B budget
I opened Claude Code on Friday night. this is what I had by Sunday ↓
what it built while I watched:
→ a full Miami-style city: palm trees, high-rises, neon signs
→ traffic that actually drives, brakes and changes lanes
→ cops that chase you when you speed. 3 cars on me in 20 seconds
→ sunset to night cycle, light bouncing off wet asphalt
→ minimap, speedometer, gearbox. it even made the HUD
zero game dev experience. never opened a game engine in my life
all it took was 3 prompts:
1. build me an open-world city like Miami. cars, traffic, cops
2. make it look like a AAA game, not a tech demo
3. fix everything that breaks, don't ask me
full prompts + setup are in my article. read it below ↓
Holy f*ck.. Anthropic CEO Dario Amodei explained why Anthropic don't hire people who write code by hand
"Writing code with AI agents is much faster and cheaper. Every engineer at Anthropic uses Claude Code"
In the same 31 minutes:
→ If revenue keeps growing 10x a year, it's $100B at the end of 2026 and $1T at the end of 2027
→ That would mean about $5 trillion of compute: $1 trillion a year for five years
→ "A part of my brain wonders if it's going to keep growing 10X"
→ Being off by just one year is enough to sink the company
Bookmark it and watch tonight
Dario won't bet the company on one optimistic guess.
Most people bet every task on one: the agent runs once, nobody checks, and they hope it's right
Harness: the room it works in
Loop: a test it has to pass before it's done
Graph: a team of agents where a judge can send the work back
Here's how to build all 3 and stop babysitting your AI agent ↓
Holy f*ck.. Anthropic engineer:
"Prompting is finally over. Anthropic team no longer write prompts by hand. We build loops"
In 29 minutes, she walks through how Anthropic went from one CLAUDE.md file to memory that agents manage on their own, and what "dreaming" is
CLAUDE.md → Memory tools → Skills → Memory as a file system → Dreaming
The model doesn't get smarter about your work on its own. The setup around it does
Memory it can read and write, rules about who can change what, and a pass that cleans it all up overnight. That's the harness
Anyone can start a new chat. Almost nobody builds agents that remember what went wrong yesterday
Bookmark it and watch tonight, then read how to build that harness in the guide below ↓
Your AI agent isn't lazy. It's homeless.
No desk. No tools. No idea what "done" means.
So you became its harness, its loop and its graph.
I broke down how to stop babysitting it in 10 steps ↓
1
30
594
Crláze retweeted
This is f*king insane... Anthropic CEO Dario Amodei just said that AI will replace ALL jobs
"We are the last generation that had to work"
In the same 3 mins:
→ Early Mythos testers called it "a super weapon" and asked Anthropic not to release it
→ Mythos found 271 new vulnerabilities in Firefox
→ He says the second biggest reason Anthropic ships so fast is Claude itself
→ His son asked to use his Claude Cowork account. His answer: "Absolutely not, I need my tokens"
Anthropic builds with Claude. These are the same building blocks, open on GitHub
Bookmark it and watch tonight
Claude ships Anthropic's products. Here's how to build the harness that lets it ship yours ↓
Holy f*ck... Anthropic CEO Dario Amodei and President Daniela Amodei on interview:
"Every programmer on Earth will be replaced by AI. The only question is who goes first"
In the same video:
→ One company found and fixed more bugs with Mythos in a week than in the whole year before
→ They refused to let the Pentagon use Claude for fully autonomous weapons or domestic mass surveillance. Could it have ended Anthropic? Daniela: "I think it crossed our minds"
→ Anthropic went from about 1,200 people to 3,500 in six months
→ Daniela isn't a software developer, and she still built a website with Claude
Bookmark it and watch tonight
If Daniela can ship a website with Claude, you can learn about Harness, Loops, Graphs ↓
Crláze retweeted
Holy sh*t.. Boris Cherny, the creator of Claude Code, says 100% of his code has been written by Claude Code since November 2025
"At any point I have a few Claudes running, sometimes hundreds, sometimes thousands"
In the same 47 minutes on Bloomberg's Odd Lots:
→ Across Anthropic, about 90% of code is written by Claude Code
→ At his Y Combinator talks, a little more than half the room now writes 100% of their code with it
→ He mostly uses Claude Code through Slack now, not the terminal
→ One engineer moved Bun from Zig to Rust in about 11 days
→ He has Tag sessions that have been running for weeks
Every repo below is free:
Claude Code itself
github.com/anthropics/claude…
Claude Code inside your PRs and issues
github.com/anthropics/claude…
Run many Claude Code agents in parallel
github.com/smtg-ai/claude-sq…
Multi-agent orchestration for Claude Code
github.com/ruvnet/ruflo
Plugins, agents and skills for Claude Code
github.com/wshobson/agents
A skills framework for agentic development
github.com/obra/superpowers
Ready-made Claude Code templates
github.com/davila7/claude-co…
Claude Code security review on every PR
github.com/anthropics/claude…
Build your own agent on Claude's loop
github.com/anthropics/claude…
Slack as an agent tool
github.com/korotovsky/slack-…
The big Claude Code resource list
github.com/hesreallyhim/awes…
All of this costs $0
One Claude is a tool. A hundred in a loop is a team
Bookmark it and watch tonight
Hundreds of Claudes only work when you stop babysitting them. The full course on harness, loops and graphs ↓
Holy f*ck.. Dario Amodei sat down with Jamie Dimon ahead of Anthropic's IPO
On white-collar jobs:
“If your job happens on a laptop, AI is already learning how to do it”
In the same 31 minutes:
→ Anthropic's revenue grew roughly 10x in 2024 and again in 2025
→ Compute is "the deepest business dilemma" the company faces, so they buy low and top up on the spot market
→ He spends 40-50% of his time on talent and culture
→ Since Mythos, customers have found hundreds of thousands of vulnerabilities
Bookmark it and watch tonight
Smarter models every few months won't help if you still babysit every run.
I wrote the full course on the harness, the loop and the graph ↓
Holy f*ck.. Anthropic just showed Wall Street what Claude can do now. Daniela Amodei, President and co-founder:
"Intelligence is now something humans can build. The implications of this are profound"
The timeline they showed:
2024: answer a question, summarize a document
2025: deep research, refactor an entire codebase
Today: "complex, open-ended projects that once took months or years", done "in days"
Their example: bringing up a new chip platform used to take dozens of engineers months. Mythos got Claude running on AMD GPUs "in just three days, with basically no human intervention", writing almost 100% of the kernels
And Dario closes with cancer, Alzheimer's, heart disease and mental illness becoming "relics of the past" in under a decade
Answers → Research → Codebases → Months of work in days
The model stopped being the bottleneck. The harness around it is the job now
Every repo below is free:
Claude Code itself
github.com/anthropics/claude…
Claude's agent loop as a library
github.com/anthropics/claude…
Anthropic's official skills
github.com/anthropics/skills
Anthropic's cookbooks
github.com/anthropics/claude…
Plugins for real knowledge work
github.com/anthropics/knowle…
Claude inside GitHub Actions
github.com/anthropics/claude…
Skills that make agents plan, test and review
github.com/obra/superpowers
Spec-driven development
github.com/github/spec-kit
The loop that keeps an agent going until it's done
github.com/snarktank/ralph
Persistent memory for Claude Code
github.com/thedotmack/claude…
Ready-made subagents
github.com/wshobson/agents
The big list of Claude Code resources
github.com/hesreallyhim/awes…
All of this costs $0
Months of work in days is only true if you know how to hand it off
Bookmark it and watch tonight
Then read the Harness, Loops, Graphs course below ↓
Your AI agent isn't lazy. It's homeless.
No desk. No tools. No idea what "done" means.
So you became its harness, its loop and its graph.
I broke down how to stop babysitting it in 10 steps ↓
3
28
648
Holy f*ck. Ex-Google CEO Eric Schmidt just told everyone how to get rich from AI in 25 seconds:
"If you really want to make money, it's actually easy"
Don't build models. Don't build platforms that design agents. Build one agent that does one thing better than anyone else
"This is the agentic period in AI"
His bet: for the next year or two, everyone builds agents and they all compete. Win one niche and you win the company
"If you build a better agent than anyone else, you can probably build one incredible company and own it yourself"
Prompts → Coding Agents → Loops → Graphs → Quality Gates → A Company You Own
Models are turning into cheap infrastructure. The money is moving to whoever runs them on one real job
Every repo below is free:
How Anthropic built its multi-agent research system
anthropic.com/engineering/bu…
Effective harnesses for long-running agents
anthropic.com/research/effec…
Build your agent on Claude Code's harness
github.com/anthropics/claude…
Agents as graphs with state you can roll back
github.com/langchain-ai/lang…
Karpathy's agents that run research on their own
github.com/karpathy/autorese…
Autonomous agent loop
github.com/snarktank/ralph
Let your agent use any website
github.com/browser-use/brows…
Visual workflow automation with built-in AI
github.com/n8n-io/n8n
Secure sandboxes for your agents
github.com/e2b-dev/E2B
Memory that carries over between sessions
github.com/mem0ai/mem0
Connect your agent to the tools your customers already use
github.com/modelcontextproto…
Anthropic's official skills, ready to drop in
github.com/anthropics/skills
All of this costs $0
The next great company won't have 50 employees. It'll have one founder and one agent nobody can beat
Bookmark it and watch tonight
Then read the Harness, Loops, Graphs course below ↓
Your AI agent isn't lazy. It's homeless.
No desk. No tools. No idea what "done" means.
So you became its harness, its loop and its graph.
I broke down how to stop babysitting it in 10 steps ↓
6
28
736
Holy f*ck... Elon Musk's team just made NVIDIA pointless with Grok Bot 1.0
Jensen held onto his job this week. His GPUs may not keep theirs
Here's what Grok Bot 1.0 can handle with no GPUs on your desk:
Every Bot you build shares a single cloud computer linked to your account, with your files, browser sessions and credentials. 53M views on the release for a reason
So your routines run at 8:30 a.m. with your PC off. Up to 300 routine runs an hour
6 always-on tasks to shift off your GPU rig, and the exact prompt:
→ X: "Every weekday at 8:30, tell me what changed on X about NVIDIA. 3 lines, a link on each"
→ Google Calendar: "Every morning by 8:30: what's on my calendar, what's overdue, what's waiting on me. Under 6 lines"
→ Zoom: "Join my calls, post the recap and action items in #team"
→ GitHub: "When a release is published, draft the changelog. The PM approves"
→ Slack: "When someone tags you in #data, reply with a chart, the query and one caveat"
→ Zendesk: "When a ticket is tagged refund, draft the reply with the ticket ID. An agent sends it"
Set one rule first: anything that posts, sends or cancels waits for my OK. Approval cards expire in 30 minutes, so decide upfront what runs without you
Give it the X prompt tonight and turn the GPU off
Then read how to build a 300-Bot company around one Bot like this in the article below ↓
44
Holy f*ck... Elon Musk's team just made NVIDIA pointless with Grok Bot 1.0
Jensen held onto his job this week. His GPUs may not keep theirs
Here's what Grok Bot 1.0 can handle with no GPUs on your desk:
Every Bot you build shares a single cloud computer linked to your account, with your files, browser sessions and credentials. 53M views on the release for a reason
So your routines run at 8:30 a.m. with your PC off. Up to 300 routine runs an hour
6 always-on tasks to shift off your GPU rig, and the exact prompt:
→ X: "Every weekday at 8:30, tell me what changed on X about NVIDIA. 3 lines, a link on each"
→ Google Calendar: "Every morning by 8:30: what's on my calendar, what's overdue, what's waiting on me. Under 6 lines"
→ Zoom: "Join my calls, post the recap and action items in #team"
→ GitHub: "When a release is published, draft the changelog. The PM approves"
→ Slack: "When someone tags you in #data, reply with a chart, the query and one caveat"
→ Zendesk: "When a ticket is tagged refund, draft the reply with the ticket ID. An agent sends it"
Set one rule first: anything that posts, sends or cancels waits for my OK. Approval cards expire in 30 minutes, so decide upfront what runs without you
Give it the X prompt tonight and turn the GPU off
Then read how to build a 300-Bot company around one Bot like this in the article below ↓
Holy f*ck. Anthropic CEO Dario Amodei says cancer, Alzheimer's, heart disease and mental illness will be relics of the past in less than a decade, and that "we can create an age of miracles"
His exact words:
"These will be relics of the past in, I think, less than a decade"
In 25 seconds, he names all four, then goes even bigger:
"I think if we do this right, we can create an age of miracles where humanity is able to solve problems that have eluded us for millennia"
This isn't a new take for him. In his 2024 essay he argued AI could compress 50 to 100 years of biology progress into 5 to 10
Models → Agents → AI Scientists → Lab Loops → An Age of Miracles
And most of the tools doing this aren't locked inside labs
Every repo below is free:
Anthropic's skills and connectors for life sciences research
github.com/anthropics/life-s…
Turn any AI agent into an AI scientist
github.com/K-Dense-AI/scient…
A general-purpose biomedical AI agent from Stanford
github.com/snap-stanford/Bio…
AlphaFold 3: predict how proteins, DNA and drugs fit together
github.com/google-deepmind/a…
The Nobel-winning protein model, open source
github.com/google-deepmind/a…
Open biomolecular interaction models
github.com/jwohlwend/boltz
Chai-1, open model for biomolecular structure
github.com/chaidiscovery/cha…
Protein language models
github.com/Biohub/esm
Design brand-new proteins from scratch
github.com/RosettaCommons/RF…
DeepMind's model for reading what DNA changes do
github.com/google-deepmind/a…
Ask questions across thousands of scientific papers
github.com/Future-House/pape…
An AI scientist, from idea to paper
github.com/SakanaAI/AI-Scien…
Deep learning for drug discovery
github.com/deepchem/deepchem
All of this costs $0
The cure won't come from one genius in a lab. It'll come from thousands of people running agents on tools like these
Bookmark it and watch tonight
Then read the Harness, Loops, Graphs course below ↓





